Instructions to use HuggingFaceTB/nanowhale-100m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/nanowhale-100m with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="HuggingFaceTB/nanowhale-100m", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/nanowhale-100m", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/nanowhale-100m", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceTB/nanowhale-100m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/nanowhale-100m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/nanowhale-100m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/nanowhale-100m

SGLang

How to use HuggingFaceTB/nanowhale-100m with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "HuggingFaceTB/nanowhale-100m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/nanowhale-100m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "HuggingFaceTB/nanowhale-100m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/nanowhale-100m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceTB/nanowhale-100m with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/nanowhale-100m
```

nanowhale-100m / README.md

cmpatino HF Staff

Add YAML metadata to model card

6a3bed5 verified 2 days ago

preview code

raw

history blame contribute delete

4.17 kB

metadata

license: apache-2.0
language:
  - en
library_name: transformers
tags:
  - deepseek
  - moe
  - causal-lm
  - sft
  - chat
datasets:
  - HuggingFaceFW/fineweb-edu
  - HuggingFaceTB/smol-smoltalk
base_model: HuggingFaceTB/nanowhale-100m-base
pipeline_tag: text-generation
model-index:
  - name: nanowhale-100m
    results: []

nanowhale-100m 🐳

A small ~110M parameter language model implementing the DeepSeek-V4 architecture, fine-tuned for chat/instruction following. Trained from scratch — no weights from DeepSeek-V4 were used.

Pretrained base model: HuggingFaceTB/nanowhale-100m-base
This model: SFT on HuggingFaceTB/smol-smoltalk
Training code: github.com/huggingface/nanowhale

Architecture

This model implements key DeepSeek-V4 innovations at a miniature scale:

Component	Details
Parameters	~110M total (41M embeddings, 69M non-embedding)
Hidden size	320
Layers	8
Attention heads	8 (1 KV head — MQA-style)
MLA	Multi-head Latent Attention with q_lora_rank=160
MoE	4 routed experts + 1 shared, top-2 routing
Hyper-Connections	hc_mult=4, Sinkhorn routing (replacing residual connections)
MTP	1 next-token prediction layer
Vocab	129,280 (DeepSeek-V4 tokenizer)
Context	2,048 tokens

Training

Stage 1: Pretraining

Dataset: HuggingFaceFW/fineweb-edu
Steps: 5,000 | Tokens: ~2.6B
Batch: 32 effective (8 × 4 GA) | Seq length: 2,048
LR: 6e-4, cosine, 3% warmup
Precision: bf16 mixed

Stage 2: SFT (this model)

Dataset: HuggingFaceTB/smol-smoltalk (460K conversations)
Steps: 3,000 | Tokens: ~72.7M
Batch: 32 effective (8 × 4 GA) | Seq length: 2,048
LR: 2e-5, cosine, 5% warmup
Precision: fp32

Metrics

Metric	Pretrained	SFT
Eval loss	—	2.607
Perplexity (held-out)	13.62	12.90
Token accuracy	33.8%	48.5%

Usage

import torch
from safetensors.torch import load_file
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
from huggingface_hub import hf_hub_download

# Load model (recommended: manual load for reliability)
config = AutoConfig.from_pretrained("HuggingFaceTB/nanowhale-100m", trust_remote_code=True)
model = AutoModelForCausalLM.from_config(config, trust_remote_code=True).float()

# Download and load weights
weights_path = hf_hub_download("HuggingFaceTB/nanowhale-100m", "model.safetensors")
state_dict = load_file(weights_path)
model.load_state_dict(state_dict, strict=True)
model = model.cuda().eval()

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/nanowhale-100m")

# Chat
messages = [{"role": "user", "content": "What are 3 benefits of exercise?"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
input_ids = tokenizer.encode(prompt, return_tensors="pt").cuda()
output = model.generate(input_ids, max_new_tokens=200, temperature=0.7, top_p=0.9,
                        pad_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(output[0][input_ids.shape[1]:], skip_special_tokens=True))

Limitations

Tiny model: 110M params with 129K vocabulary — most capacity goes to embeddings. Generations are often incoherent or factually wrong.
Undertrained: Only 5K pretrain + 3K SFT steps. Production models train for 100K+ steps on trillions of tokens.
Educational purpose: This model demonstrates the DeepSeek-V4 architecture at small scale. It is not suitable for any production use.
bf16 NaN: Use fp32 — the Hyper-Connections architecture produces values that overflow bf16 range at this scale.
Custom code: Requires trust_remote_code=True.

Hardware

Trained on 1× NVIDIA H100 80GB.

License

Apache-2.0